Two-stepped majority voting for efficient EEG-based emotion classification
Abstract In this paper, a novel approach that is based on two-stepped majority voting is proposed for efficient EEG-based emotion classification. Emotion recognition is important for human–machine interactions. Facial features- and body gestures-based approaches have been generally proposed for emot...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
SpringerOpen
2020-09-01
|
Series: | Brain Informatics |
Subjects: | |
Online Access: | http://link.springer.com/article/10.1186/s40708-020-00111-3 |
id |
doaj-cc7752225e2f4b3faeab56293dddbc23 |
---|---|
record_format |
Article |
spelling |
doaj-cc7752225e2f4b3faeab56293dddbc232020-11-25T01:29:01ZengSpringerOpenBrain Informatics2198-40182198-40262020-09-017111210.1186/s40708-020-00111-3Two-stepped majority voting for efficient EEG-based emotion classificationAras M. Ismael0Ömer F. Alçin1Karmand Hussein Abdalla2Abdulkadir Şengür3Sulaimani Polytechnic UniversityElectrical Engineering Department, Engineering and Natural Sciences Faculty, Malatya Turgut Ozal UniversityPsychology Department, Raparin UniversityElectrical-Electronics Engineering Department, Technology Faculty, Firat UniversityAbstract In this paper, a novel approach that is based on two-stepped majority voting is proposed for efficient EEG-based emotion classification. Emotion recognition is important for human–machine interactions. Facial features- and body gestures-based approaches have been generally proposed for emotion recognition. Recently, EEG-based approaches become more popular in emotion recognition. In the proposed approach, the raw EEG signals are initially low-pass filtered for noise removal and band-pass filters are used for rhythms extraction. For each rhythm, the best performed EEG channels are determined based on wavelet-based entropy features and fractal dimension-based features. The k-nearest neighbor (KNN) classifier is used in classification. The best five EEG channels are used in majority voting for getting the final predictions for each EEG rhythm. In the second majority voting step, the predictions from all rhythms are used to get a final prediction. The DEAP dataset is used in experiments and classification accuracy, sensitivity and specificity are used for performance evaluation metrics. The experiments are carried out to classify the emotions into two binary classes such as high valence (HV) vs low valence (LV) and high arousal (HA) vs low arousal (LA). The experiments show that 86.3% HV vs LV discrimination accuracy and 85.0% HA vs LA discrimination accuracy is obtained. The obtained results are also compared with some of the existing methods. The comparisons show that the proposed method has potential in the use of EEG-based emotion classification.http://link.springer.com/article/10.1186/s40708-020-00111-3EEG-based emotion recognitionEEG rhythmsWavelet packet entropiesFractal dimensionsMajority voting |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Aras M. Ismael Ömer F. Alçin Karmand Hussein Abdalla Abdulkadir Şengür |
spellingShingle |
Aras M. Ismael Ömer F. Alçin Karmand Hussein Abdalla Abdulkadir Şengür Two-stepped majority voting for efficient EEG-based emotion classification Brain Informatics EEG-based emotion recognition EEG rhythms Wavelet packet entropies Fractal dimensions Majority voting |
author_facet |
Aras M. Ismael Ömer F. Alçin Karmand Hussein Abdalla Abdulkadir Şengür |
author_sort |
Aras M. Ismael |
title |
Two-stepped majority voting for efficient EEG-based emotion classification |
title_short |
Two-stepped majority voting for efficient EEG-based emotion classification |
title_full |
Two-stepped majority voting for efficient EEG-based emotion classification |
title_fullStr |
Two-stepped majority voting for efficient EEG-based emotion classification |
title_full_unstemmed |
Two-stepped majority voting for efficient EEG-based emotion classification |
title_sort |
two-stepped majority voting for efficient eeg-based emotion classification |
publisher |
SpringerOpen |
series |
Brain Informatics |
issn |
2198-4018 2198-4026 |
publishDate |
2020-09-01 |
description |
Abstract In this paper, a novel approach that is based on two-stepped majority voting is proposed for efficient EEG-based emotion classification. Emotion recognition is important for human–machine interactions. Facial features- and body gestures-based approaches have been generally proposed for emotion recognition. Recently, EEG-based approaches become more popular in emotion recognition. In the proposed approach, the raw EEG signals are initially low-pass filtered for noise removal and band-pass filters are used for rhythms extraction. For each rhythm, the best performed EEG channels are determined based on wavelet-based entropy features and fractal dimension-based features. The k-nearest neighbor (KNN) classifier is used in classification. The best five EEG channels are used in majority voting for getting the final predictions for each EEG rhythm. In the second majority voting step, the predictions from all rhythms are used to get a final prediction. The DEAP dataset is used in experiments and classification accuracy, sensitivity and specificity are used for performance evaluation metrics. The experiments are carried out to classify the emotions into two binary classes such as high valence (HV) vs low valence (LV) and high arousal (HA) vs low arousal (LA). The experiments show that 86.3% HV vs LV discrimination accuracy and 85.0% HA vs LA discrimination accuracy is obtained. The obtained results are also compared with some of the existing methods. The comparisons show that the proposed method has potential in the use of EEG-based emotion classification. |
topic |
EEG-based emotion recognition EEG rhythms Wavelet packet entropies Fractal dimensions Majority voting |
url |
http://link.springer.com/article/10.1186/s40708-020-00111-3 |
work_keys_str_mv |
AT arasmismael twosteppedmajorityvotingforefficienteegbasedemotionclassification AT omerfalcin twosteppedmajorityvotingforefficienteegbasedemotionclassification AT karmandhusseinabdalla twosteppedmajorityvotingforefficienteegbasedemotionclassification AT abdulkadirsengur twosteppedmajorityvotingforefficienteegbasedemotionclassification |
_version_ |
1725099067706441728 |